95f76d7ffb
The ups-shutdown-cluster.sh script was missing LXC container shutdown functionality, only shutting down VMs. This could leave containers running during UPS power failure, causing ungraceful shutdown. Changes: - Added Step 2: LXC container shutdown on all cluster nodes - Uses 'pct list' to find running containers - Shuts down each container with 60s timeout - Parallel shutdown with '&' for speed - Both local (pvemini) and remote nodes (pve1, pveelite) - Updated step numbers (now 6 steps total vs 5 before) - Fixed log_message() to use dynamic timestamp - Fixed node name comment (pve2 → pveelite) Shutdown order: 1. VMs on all nodes (timeout 60s) 2. LXC containers on all nodes (timeout 60s) [NEW] 3. Wait 90 seconds for graceful shutdown 4. Secondary nodes shutdown (pve1, pveelite) 5. Wait 30 seconds 6. Primary node shutdown (pvemini) This matches the behavior in ups-maintenance-shutdown.sh which already had LXC support. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
114 lines
3.9 KiB
Bash
114 lines
3.9 KiB
Bash
#!/bin/bash
|
|
#
|
|
# Script de shutdown orchestrat pentru cluster Proxmox când UPS este pe baterie critică
|
|
# Autor: Generat automat
|
|
# Data: 2025-10-06
|
|
# Actualizat: 2025-10-06 - Adăugat suport LXC containers
|
|
|
|
LOGFILE=/var/log/ups-shutdown.log
|
|
NODES=(10.0.20.200 10.0.20.202) # pve1, pveelite (pvemini va fi ultimul)
|
|
|
|
log_message() {
|
|
echo "[$(date '+%Y-%m-%d %H:%M:%S')] $1" | tee -a $LOGFILE
|
|
}
|
|
|
|
log_message "========================================"
|
|
log_message "UPS SHUTDOWN ORCHESTRATION STARTED"
|
|
log_message "UPS Status: $(upsc nutdev1 ups.status 2>/dev/null || echo 'UNKNOWN')"
|
|
log_message "Battery Charge: $(upsc nutdev1 battery.charge 2>/dev/null || echo 'UNKNOWN')%"
|
|
log_message "========================================"
|
|
|
|
# Verifică dacă UPS este într-adevăr pe baterie critică
|
|
UPS_STATUS=$(upsc nutdev1 ups.status 2>/dev/null)
|
|
if [[ ! $UPS_STATUS =~ (OB|LB) ]]; then
|
|
log_message "WARNING: UPS status is $UPS_STATUS - not critical. Aborting shutdown."
|
|
exit 0
|
|
fi
|
|
|
|
log_message "Step 1: Oprire VM-uri pe toate nodurile..."
|
|
|
|
# Oprește VM-uri pe toate nodurile (inclusiv local)
|
|
for node in ${NODES[@]} localhost; do
|
|
if [ "$node" == "localhost" ]; then
|
|
NODE_NAME="pvemini (local)"
|
|
else
|
|
NODE_NAME=$node
|
|
fi
|
|
|
|
log_message " - Oprire VM-uri pe $NODE_NAME..."
|
|
|
|
if [ "$node" == "localhost" ]; then
|
|
# Local - oprește VM-urile direct
|
|
for vmid in $(qm list | awk 'NR>1 {print $1}'); do
|
|
vm_status=$(qm status $vmid | awk '{print $2}')
|
|
if [ "$vm_status" == "running" ]; then
|
|
log_message " * Oprire VM $vmid pe pvemini..."
|
|
qm shutdown $vmid --timeout 60 &
|
|
fi
|
|
done
|
|
else
|
|
# Remote - SSH către alt nod
|
|
ssh -o ConnectTimeout=5 root@$node "
|
|
for vmid in \$(qm list | awk 'NR>1 {print \$1}'); do
|
|
vm_status=\$(qm status \$vmid | awk '{print \$2}')
|
|
if [ \"\$vm_status\" == \"running\" ]; then
|
|
echo ' * Oprire VM '\$vmid' pe $node...'
|
|
qm shutdown \$vmid --timeout 60 &
|
|
fi
|
|
done
|
|
" 2>&1 | tee -a $LOGFILE
|
|
fi
|
|
done
|
|
|
|
log_message "Step 2: Oprire containere LXC pe toate nodurile..."
|
|
|
|
# Oprește containere LXC pe toate nodurile
|
|
for node in ${NODES[@]} localhost; do
|
|
if [ "$node" == "localhost" ]; then
|
|
NODE_NAME="pvemini (local)"
|
|
else
|
|
NODE_NAME=$node
|
|
fi
|
|
|
|
log_message " - Oprire LXC pe $NODE_NAME..."
|
|
|
|
if [ "$node" == "localhost" ]; then
|
|
# Local - oprește containerele direct
|
|
pct list 2>/dev/null | awk 'NR>1 && $2=="running" {print $1}' | while read ctid; do
|
|
log_message " * Oprire container $ctid pe pvemini..."
|
|
pct shutdown $ctid --timeout 60 &
|
|
done
|
|
else
|
|
# Remote - SSH către alt nod
|
|
ssh -o ConnectTimeout=5 root@$node "
|
|
pct list 2>/dev/null | awk 'NR>1 && \$2==\"running\" {print \$1}' | while read ctid; do
|
|
echo ' * Oprire container '\$ctid' pe $node...'
|
|
pct shutdown \$ctid --timeout 60 &
|
|
done
|
|
" 2>&1 | tee -a $LOGFILE
|
|
fi
|
|
done
|
|
|
|
log_message "Step 3: Așteptare 90 secunde pentru oprirea VM-urilor și LXC..."
|
|
sleep 90
|
|
|
|
log_message "Step 4: Oprire noduri secundare (pve1, pveelite)..."
|
|
for node in ${NODES[@]}; do
|
|
log_message " - Shutdown nod $node..."
|
|
ssh -o ConnectTimeout=5 root@$node "shutdown -h +1 'UPS on battery critical - shutting down'" 2>&1 | tee -a $LOGFILE &
|
|
done
|
|
|
|
log_message "Step 5: Așteptare 30 secunde pentru shutdown noduri secundare..."
|
|
sleep 30
|
|
|
|
log_message "Step 6: Oprire nod local (pvemini - primary)..."
|
|
log_message "========================================"
|
|
log_message "UPS SHUTDOWN ORCHESTRATION COMPLETED"
|
|
log_message "Local node will shutdown in 1 minute"
|
|
log_message "========================================"
|
|
|
|
# Oprește nodul local (ultimul)
|
|
shutdown -h +1 "UPS on battery critical - primary node shutting down"
|
|
|
|
exit 0
|