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
61 lines
2.2 KiB
Bash
Executable File
61 lines
2.2 KiB
Bash
Executable File
#!/bin/bash
|
|
# install-utils.sh - installs useful observability packages on a host.
|
|
# These are all small, dependency-light, and read-only at runtime.
|
|
set -uo pipefail
|
|
SSH_OPTS=(-o BatchMode=yes -o ConnectTimeout=8 -o StrictHostKeyChecking=accept-new)
|
|
|
|
HOSTS=(pfv-tsys6 pfv-tsys7)
|
|
|
|
# Packages to install, with rationale
|
|
PKGS=(
|
|
sysstat # sar, iostat, mpstat, pidstat - the missing observability suite
|
|
jq # JSON parsing for pvesh/scripts
|
|
numactl # NUMA topology/controls for the dual-socket hosts
|
|
nvme-cli # NVMe health (for when NVMe shows up)
|
|
tcpdump # packet capture for network debugging
|
|
mtr-tiny # traceroute on steroids
|
|
nstat # kernel SNMP stats (already partly there)
|
|
dnsutils # dig, nslookup, host
|
|
bmon # bandwidth monitor ( curses, real-time)
|
|
)
|
|
|
|
for host in "${HOSTS[@]}"; do
|
|
echo "================================================================"
|
|
echo "[$host] installing observability packages"
|
|
echo "================================================================"
|
|
|
|
if ! ssh "${SSH_OPTS[@]}" "root@$host" 'echo ok' >/dev/null 2>&1; then
|
|
echo " UNREACHABLE"
|
|
continue
|
|
fi
|
|
|
|
# Check which are missing
|
|
missing=""
|
|
for pkg in "${PKGS[@]}"; do
|
|
if ! ssh "${SSH_OPTS[@]}" "root@$host" "dpkg -s $pkg 2>/dev/null | grep -q 'Status: install ok installed'" 2>/dev/null; then
|
|
missing="$missing $pkg"
|
|
fi
|
|
done
|
|
|
|
if [ -z "$missing" ]; then
|
|
echo " All packages already installed."
|
|
continue
|
|
fi
|
|
|
|
echo " Installing:$missing"
|
|
ssh "${SSH_OPTS[@]}" "root@$host" \
|
|
"DEBIAN_FRONTEND=noninteractive apt-get update -qq >/dev/null 2>&1 && \
|
|
DEBIAN_FRONTEND=noninteractive apt-get install -y -qq$missing 2>&1 | tail -5"
|
|
echo " Done."
|
|
echo ""
|
|
done
|
|
|
|
# Enable sysstat data collection (sar) — off by default on Debian
|
|
for host in "${HOSTS[@]}"; do
|
|
echo "[$host] enabling sysstat/sar data collection..."
|
|
ssh "${SSH_OPTS[@]}" "root@$host" \
|
|
"sed -i 's/^ENABLED=\"false\"/ENABLED=\"true\"/' /etc/default/sysstat 2>/dev/null; \
|
|
systemctl enable --now sysstat 2>&1 | tail -2; \
|
|
grep ENABLED /etc/default/sysstat"
|
|
done
|