mrcharles
422999bf3c
Performance optimization engagement for a 7-host Proxmox R&D cluster.
Captures the accumulated work across host tuning, network analysis,
fleet assessment, and kubernetes architecture planning.
Contents:
- Host-side tunings (scripts/): CPU governor, swappiness, BBR, NFS
nconnect, tuned profiles -- complete on 5 of 7 hosts
- Validation + benchmarking scripts: iperf matrix, bond/NFS fixes
- Collected host data (returned-logs/): check.sh output from all 7
hosts + iperf results, including newly-validated pfv-tsys9
- AGENTS.md: operating context for AI agents
- PROJECT.md: board-ready fleet assessment with VM placement and
storage redundancy analysis (40 VMs across 7 hosts)
- K8S.md: kubernetes architecture deep-dive covering cnode/wnode
distribution, StorageClass design, and ETL/HPC workload planning
💘 Generated with Crush
Assisted-by: Crush:glm-5.2
59 lines
2.3 KiB
Bash
Executable File
59 lines
2.3 KiB
Bash
Executable File
#!/bin/bash
|
||
# wait-for-host.sh - polls SSH until host is back, then runs verification.
|
||
# Usage: bash wait-for-host.sh <host>
|
||
set -uo pipefail
|
||
HOST="$1"
|
||
SSH_OPTS=(-o BatchMode=yes -o ConnectTimeout=5 -o ServerAliveInterval=5 -o StrictHostKeyChecking=accept-new)
|
||
|
||
DEADLINE=$(( $(date +%s) + 600 ))
|
||
echo "Polling $HOST for SSH return (max 10 min)..."
|
||
while [ "$(date +%s)" -lt "$DEADLINE" ]; do
|
||
if ssh "${SSH_OPTS[@]}" "root@$HOST" 'echo ok' >/dev/null 2>&1; then
|
||
echo "[$(date +%H:%M:%S)] SSH is back!"
|
||
break
|
||
fi
|
||
sleep 10
|
||
echo " [$(date +%H:%M:%S)] still down..."
|
||
done
|
||
|
||
if ! ssh "${SSH_OPTS[@]}" "root@$HOST" 'echo ok' >/dev/null 2>&1; then
|
||
echo "FAILED: $HOST not back after 10 minutes"
|
||
exit 1
|
||
fi
|
||
|
||
echo "Waiting 30s for services to settle..."
|
||
sleep 30
|
||
|
||
echo ""
|
||
echo "================================================================"
|
||
echo "[$HOST] POST-REBOOT VERIFICATION"
|
||
echo "================================================================"
|
||
echo "--- Uptime (should be < 5 min) ---"
|
||
ssh "${SSH_OPTS[@]}" "root@$HOST" 'uptime'
|
||
echo ""
|
||
echo "--- TCP congestion control (expect bbr) ---"
|
||
ssh "${SSH_OPTS[@]}" "root@$HOST" 'sysctl net.ipv4.tcp_congestion_control net.core.default_qdisc'
|
||
echo ""
|
||
echo "--- vm.swappiness ---"
|
||
ssh "${SSH_OPTS[@]}" "root@$HOST" 'sysctl vm.swappiness'
|
||
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)"'
|
||
echo ""
|
||
echo "--- NFS mount options (looking for nconnect=4 + noatime) ---"
|
||
ssh "${SSH_OPTS[@]}" "root@$HOST" 'nfsstat -m 2>/dev/null | head -16'
|
||
echo ""
|
||
echo "--- NFS TCP connection count to :2049 (expect ~8 = 4 per server × 2 servers) ---"
|
||
ssh "${SSH_OPTS[@]}" "root@$HOST" 'ss -tn state established "( dport = :2049 )" 2>/dev/null'
|
||
ssh "${SSH_OPTS[@]}" "root@$HOST" 'ss -tn state established "( dport = :2049 )" 2>/dev/null | tail -n +2 | wc -l'
|
||
echo ""
|
||
echo "--- Running VMs ---"
|
||
ssh "${SSH_OPTS[@]}" "root@$HOST" 'qm list 2>/dev/null'
|
||
echo ""
|
||
echo "--- Failed services ---"
|
||
ssh "${SSH_OPTS[@]}" "root@$HOST" 'systemctl --failed --no-legend 2>/dev/null | head -10'
|
||
echo ""
|
||
echo "================================================================"
|
||
echo "[$HOST] DONE"
|
||
echo "================================================================"
|