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
42 lines
2.3 KiB
Bash
Executable File
42 lines
2.3 KiB
Bash
Executable File
#!/bin/bash
|
|
# check-repos-and-reboot.sh - checks reboot-required + Proxmox repo config on all hosts.
|
|
set -uo pipefail
|
|
SSH_OPTS=(-o BatchMode=yes -o ConnectTimeout=8 -o StrictHostKeyChecking=accept-new)
|
|
HOSTS=(pfv-tsys1 pfv-tsys3 pfv-tsys4 pfv-tsys5 pfv-tsys6 pfv-tsys7)
|
|
|
|
for host in "${HOSTS[@]}"; do
|
|
echo "================================================================"
|
|
echo "[$host]"
|
|
echo "================================================================"
|
|
|
|
if ! ssh "${SSH_OPTS[@]}" "root@$host" 'echo ok' >/dev/null 2>&1; then
|
|
echo " UNREACHABLE"
|
|
continue
|
|
fi
|
|
|
|
echo "--- /var/run/reboot-required ---"
|
|
ssh "${SSH_OPTS[@]}" "root@$host" 'if [ -r /var/run/reboot-required ]; then echo "REBOOT REQUIRED"; cat /var/run/reboot-required 2>/dev/null; if [ -r /var/run/reboot-required.pkgs ]; then echo "Packages triggering:"; cat /var/run/reboot-required.pkgs; fi; else echo "(no reboot required marker)"; fi'
|
|
|
|
echo ""
|
|
echo "--- Running kernel vs installed kernel ---"
|
|
ssh "${SSH_OPTS[@]}" "root@$host" 'echo "running: $(uname -r)"; echo "installed:"; dpkg -l | grep -E "pve-kernel-[0-9]" | awk "{print \" \"\$2\" \"\$3}" | tail -5'
|
|
|
|
echo ""
|
|
echo "--- Proxmox repositories (apt sources) ---"
|
|
ssh "${SSH_OPTS[@]}" "root@$host" 'grep -rh "pve\|proxmox" /etc/apt/sources.list /etc/apt/sources.list.d/ 2>/dev/null | grep -v "^#" | sed "s/^/ /"'
|
|
|
|
echo ""
|
|
echo "--- Enterprise repo status (should be commented or absent if no subscription) ---"
|
|
ssh "${SSH_OPTS[@]}" "root@$host" 'grep -l "pve-enterprise" /etc/apt/sources.list /etc/apt/sources.list.d/* 2>/dev/null | while read f; do echo " File: $f"; grep -n "pve-enterprise" "$f" | sed "s/^/ /"; done'
|
|
|
|
echo ""
|
|
echo "--- no-subscription repo presence ---"
|
|
ssh "${SSH_OPTS[@]}" "root@$host" 'grep -rl "pve-no-subscription" /etc/apt/sources.list /etc/apt/sources.list.d/ 2>/dev/null | while read f; do echo " File: $f"; grep -n "pve-no-subscription" "$f" | sed "s/^/ /"; done'
|
|
|
|
echo ""
|
|
echo "--- Recently updated packages (last 24h, kernel-related) ---"
|
|
ssh "${SSH_OPTS[@]}" "root@$host" 'grep -E "pve-kernel|proxmox|pve-qemu|zfs" /var/log/dpkg.log 2>/dev/null | grep "$(date +%Y-%m-%d)\|$(date -d yesterday +%Y-%m-%d)" | tail -15 || echo "(none in dpkg.log)"'
|
|
|
|
echo ""
|
|
done
|