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
52 lines
2.0 KiB
Bash
Executable File
52 lines
2.0 KiB
Bash
Executable File
#!/bin/bash
|
|
# deploy-and-fix.sh - uploads fix script, runs it, starts VMs, verifies.
|
|
set -uo pipefail
|
|
HOST="$1"
|
|
SSH_OPTS=(-o BatchMode=yes -o ConnectTimeout=8 -o ServerAliveInterval=10 -o StrictHostKeyChecking=accept-new)
|
|
SCRIPT_DIR="/home/reachableceo/projects/perfopt/scripts"
|
|
|
|
echo "=== Uploading fix script to $HOST ==="
|
|
scp "${SSH_OPTS[@]}" "$SCRIPT_DIR/fix-bond-nfs.sh" "root@$HOST:/root/fix-bond-nfs.sh" >/dev/null 2>&1
|
|
|
|
echo "=== Running fix ==="
|
|
ssh "${SSH_OPTS[@]}" "root@$HOST" 'chmod +x /root/fix-bond-nfs.sh && bash /root/fix-bond-nfs.sh' 2>&1
|
|
|
|
echo ""
|
|
echo "=== Starting VMs ==="
|
|
for vmid in $(ssh "${SSH_OPTS[@]}" "root@$HOST" 'qm list 2>/dev/null | awk "NR>1{print \$1}"'); do
|
|
status=$(ssh "${SSH_OPTS[@]}" "root@$HOST" "qm status $vmid 2>/dev/null | awk '{print \$2}'")
|
|
if [ "$status" != "running" ]; then
|
|
echo " Starting VM $vmid..."
|
|
ssh "${SSH_OPTS[@]}" "root@$HOST" "qm start $vmid" 2>&1 | sed 's/^/ /'
|
|
else
|
|
echo " VM $vmid already running"
|
|
fi
|
|
done
|
|
|
|
echo ""
|
|
echo "Waiting 20s for VMs to boot..."
|
|
sleep 20
|
|
|
|
echo ""
|
|
echo "=== FULL VERIFICATION ==="
|
|
echo ""
|
|
echo "--- VMs ---"
|
|
ssh "${SSH_OPTS[@]}" "root@$HOST" 'qm list'
|
|
echo ""
|
|
echo "--- NFS mounts ---"
|
|
ssh "${SSH_OPTS[@]}" "root@$HOST" 'nfsstat -m 2>/dev/null | head -24'
|
|
echo ""
|
|
echo "--- NFS TCP connections ---"
|
|
ssh "${SSH_OPTS[@]}" "root@$HOST" 'ss -tn state established "( dport = :2049 )" 2>/dev/null'
|
|
echo " Count:"
|
|
ssh "${SSH_OPTS[@]}" "root@$HOST" 'ss -tn state established "( dport = :2049 )" 2>/dev/null | tail -n +2 | wc -l'
|
|
echo ""
|
|
echo "--- bond0 hash policy ---"
|
|
ssh "${SSH_OPTS[@]}" "root@$HOST" 'cat /proc/net/bonding/bond0 | head -6'
|
|
echo ""
|
|
echo "--- Summary ---"
|
|
ssh "${SSH_OPTS[@]}" "root@$HOST" 'echo "tcp_cc: $(sysctl -n net.ipv4.tcp_congestion_control)"'
|
|
ssh "${SSH_OPTS[@]}" "root@$HOST" 'echo "swappiness: $(sysctl -n vm.swappiness)"'
|
|
ssh "${SSH_OPTS[@]}" "root@$HOST" 'echo "governor: $(cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_governor 2>/dev/null)"'
|
|
ssh "${SSH_OPTS[@]}" "root@$HOST" 'tuned-adm active 2>/dev/null'
|