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
56 lines
1.8 KiB
Bash
56 lines
1.8 KiB
Bash
#!/usr/bin/env bash
|
|
# Probe conman state + expect availability on pfv-tsys4.
|
|
# Read-only. Decides whether we drive via conman+expect or expect-only.
|
|
set -u
|
|
|
|
# De-conflict: any ssh to pfv-tsys4 right now?
|
|
echo "===== LOCAL ssh activity ====="
|
|
ps -eo pid,etime,args | grep -E 'ssh.*pfv-tsys' | grep -v grep || echo "(none to pfv-tsys4)"
|
|
|
|
echo
|
|
echo "===== pfv-tsys4: conman + expect state ====="
|
|
ssh -o BatchMode=yes -o ConnectTimeout=5 root@pfv-tsys4 'bash -s' <<'REMOTE'
|
|
echo "--- conmand service ---"
|
|
systemctl is-active conmand 2>&1 || true
|
|
systemctl is-enabled conmand 2>&1 || true
|
|
systemctl status conmand --no-pager 2>&1 | head -15 || true
|
|
|
|
echo
|
|
echo "--- conman binary ---"
|
|
command -v conman && conman --version 2>&1 | head -2 || echo "conman: MISSING"
|
|
command -v conmand && echo "conmand present" || echo "conmand: MISSING"
|
|
|
|
echo
|
|
echo "--- /etc/conman.conf: ttyUSB2 entries ---"
|
|
grep -nE "ttyUSB2|core-sw|CONSOLE|LOG|SERIAL|BAUD" /etc/conman.conf 2>/dev/null | head -40 || echo "(no matches / no file)"
|
|
|
|
echo
|
|
echo "--- conman log dir ---"
|
|
ls -la /var/log/conman/ 2>&1 | head -20 || echo "(no /var/log/conman)"
|
|
ls -la /var/consoles/ 2>&1 | head -20 || echo "(no /var/consoles)"
|
|
|
|
echo
|
|
echo "--- expect availability ---"
|
|
command -v expect && expect -v 2>&1 || echo "expect: NOT installed"
|
|
echo "apt-cache policy expect:"
|
|
apt-cache policy expect 2>/dev/null | head -10 || echo "(apt-cache failed)"
|
|
|
|
echo
|
|
echo "--- other useful drivers ---"
|
|
for t in tclsh socat cu tip; do
|
|
command -v "$t" 2>/dev/null && echo " $t: present" || true
|
|
done
|
|
|
|
echo
|
|
echo "--- apt network reachability (quick) ---"
|
|
timeout 5 bash -c 'echo > /dev/tcp/deb.debian.org/80' 2>&1 && echo "apt network: OK" || echo "apt network: UNREACHABLE"
|
|
|
|
echo
|
|
echo "--- disk space for log ---"
|
|
df -h /root 2>&1 | tail -2
|
|
|
|
echo
|
|
echo "--- screen sessions (still 3?) ---"
|
|
screen -ls 2>&1 || true
|
|
REMOTE
|