mrcharles
4851517947
Reorganize the merged KNELServerBuild + PFVCluster repo:
provisioning/ server provisioning (was ProjectCode/ +
Project-Includes/ + Project-ConfigFiles/)
tests/ test suite (was Project-Tests/)
perf/ Proxmox perf scripts (was top-level *.sh + scripts/)
docs/ all documentation (was ProjectDocs/ + PROJECT.md +
K8S.md + TODO.md)
dns-cluster-setup/ Technitium DNS cluster (unchanged)
netinfra/ netinfra audit scripts (unchanged)
switches/ switch configs (unchanged)
vendor/ vendored KNELShellFramework (unchanged)
Update all internal path references from old directory names
(ProjectCode/, Project-Includes/, Project-Tests/) to the new ones
(provisioning/, tests/) across all scripts.
🤖 Generated with [Crush](https://github.com/charmassociates/crush)
Assisted-by: GLM-5 via Crush <crush@charm.land>
92 lines
3.7 KiB
Bash
Executable File
92 lines
3.7 KiB
Bash
Executable File
#!/bin/bash
|
|
# reboot-verify.sh - reboots a host, waits for it to come back, verifies state.
|
|
# Usage: bash reboot-verify.sh <host>
|
|
set -uo pipefail
|
|
|
|
HOST="$1"
|
|
SSH_OPTS=(-o BatchMode=yes -o ConnectTimeout=5 -o ServerAliveInterval=5 -o StrictHostKeyChecking=accept-new)
|
|
|
|
echo "================================================================"
|
|
echo "[$HOST] PRE-REBOOT STATE"
|
|
echo "================================================================"
|
|
echo "--- Running VMs ---"
|
|
ssh "${SSH_OPTS[@]}" "root@$HOST" 'qm list 2>/dev/null | awk "NR==1 || \$3==\"running\"{print}"' 2>&1
|
|
echo "--- NFS mount count ---"
|
|
ssh "${SSH_OPTS[@]}" "root@$HOST" 'nfsstat -m 2>/dev/null | grep -c "^/mnt"' 2>&1
|
|
echo "--- NFS TCP connections to :2049 ---"
|
|
ssh "${SSH_OPTS[@]}" "root@$HOST" 'ss -tn state established "( dport = :2049 )" 2>/dev/null | tail -n +2 | wc -l' 2>&1
|
|
echo "--- Uptime ---"
|
|
ssh "${SSH_OPTS[@]}" "root@$HOST" 'uptime' 2>&1
|
|
|
|
echo ""
|
|
echo "================================================================"
|
|
echo "[$HOST] ISSUING REBOOT"
|
|
echo "================================================================"
|
|
# Issue reboot; ssh will disconnect with non-zero — that's expected.
|
|
ssh "${SSH_OPTS[@]}" "root@$HOST" 'nohup sh -c "(sleep 2; systemctl reboot)" >/dev/null 2>&1 &' 2>&1
|
|
echo "Reboot command sent at $(date +%H:%M:%S). Host will drop now."
|
|
|
|
echo ""
|
|
echo "================================================================"
|
|
echo "[$HOST] WAITING FOR SSH TO RETURN (max 10 minutes)"
|
|
echo "================================================================"
|
|
DEADLINE=$(( $(date +%s) + 600 ))
|
|
LAST_PRINT=0
|
|
while [ "$(date +%s)" -lt "$DEADLINE" ]; do
|
|
now=$(date +%s)
|
|
# Print a heartbeat every 15s
|
|
if [ $((now - LAST_PRINT)) -ge 15 ]; then
|
|
elapsed=$((DEADLINE - now - 600)); elapsed=${elapsed#-}
|
|
echo " [$(date +%H:%M:%S)] still waiting... (${elapsed}s elapsed)"
|
|
LAST_PRINT=$now
|
|
fi
|
|
# Try SSH
|
|
if ssh "${SSH_OPTS[@]}" "root@$HOST" 'echo ok' >/dev/null 2>&1; then
|
|
echo " [$(date +%H:%M:%S)] SSH is back!"
|
|
break
|
|
fi
|
|
sleep 5
|
|
done
|
|
|
|
# Final check
|
|
if ! ssh "${SSH_OPTS[@]}" "root@$HOST" 'echo ok' >/dev/null 2>&1; then
|
|
echo " [$(date +%H:%M:%S)] FAILED: host not reachable after 10 minutes"
|
|
exit 1
|
|
fi
|
|
|
|
# Give services a moment to settle after SSH returns
|
|
echo " Waiting 20s for services to settle..."
|
|
sleep 20
|
|
|
|
echo ""
|
|
echo "================================================================"
|
|
echo "[$HOST] POST-REBOOT VERIFICATION"
|
|
echo "================================================================"
|
|
echo "--- Uptime ---"
|
|
ssh "${SSH_OPTS[@]}" "root@$HOST" 'uptime' 2>&1
|
|
echo ""
|
|
echo "--- TCP congestion control ---"
|
|
ssh "${SSH_OPTS[@]}" "root@$HOST" 'sysctl net.ipv4.tcp_congestion_control net.core.default_qdisc' 2>&1
|
|
echo ""
|
|
echo "--- vm.swappiness ---"
|
|
ssh "${SSH_OPTS[@]}" "root@$HOST" 'sysctl vm.swappiness' 2>&1
|
|
echo ""
|
|
echo "--- scaling_governor ---"
|
|
ssh "${SSH_OPTS[@]}" "root@$HOST" 'cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_governor 2>/dev/null || echo "(no cpufreq driver)"' 2>&1
|
|
echo ""
|
|
echo "--- NFS mount options (looking for nconnect + noatime) ---"
|
|
ssh "${SSH_OPTS[@]}" "root@$HOST" 'nfsstat -m 2>/dev/null | head -20' 2>&1
|
|
echo ""
|
|
echo "--- NFS TCP connection count (expect ~8 = 4 per server with nconnect=4) ---"
|
|
ssh "${SSH_OPTS[@]}" "root@$HOST" 'ss -tn state established "( dport = :2049 )" 2>/dev/null | tail -n +2 | wc -l' 2>&1
|
|
echo ""
|
|
echo "--- Running VMs ---"
|
|
ssh "${SSH_OPTS[@]}" "root@$HOST" 'qm list 2>/dev/null' 2>&1
|
|
echo ""
|
|
echo "--- Failed services? ---"
|
|
ssh "${SSH_OPTS[@]}" "root@$HOST" 'systemctl --failed --no-legend 2>/dev/null | head -10' 2>&1
|
|
echo ""
|
|
echo "================================================================"
|
|
echo "[$HOST] DONE"
|
|
echo "================================================================"
|