pastilhasandClaude Opus 5
6ffd3534bd
Servers only now. On a machine you sit at, a filling disk announces itself — the editor refuses to save, the browser complains — and you are there to deal with it. The reserve is for the box nobody is watching, where the first sign is a service that stopped working hours ago. Skipped rather than asked, but said out loud with the reason and recorded in the summary. A section that silently produces no output is indistinguishable from one that failed. The cron this section installs was already there and is unchanged: /etc/cron.d runs the checker as root every ten minutes, and it deletes the ballast when free space falls under the threshold. What changed is where its message goes. Both alerts now run through one notify() inside the generated checker rather than calling logger directly, so there is a single place to add a second channel. Today it is still syslog only — the message lands in the journal and nowhere else, so nobody learns about it until they go looking, which is precisely the wrong moment. Push, mail or Officer's own notify sidecar hook in there. It also echoes to stderr now, so running the checker by hand shows the message instead of appearing to do nothing. Verified: dev reports not-applicable and asks nothing, vps still asks and records a refusal, and the regenerated checker parses and reports status. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
676 lines
27 KiB
Bash
Executable File
676 lines
27 KiB
Bash
Executable File
#!/bin/bash
|
|
set -e
|
|
|
|
# =============================================================================
|
|
# machine-setup — provisioning for a fresh machine
|
|
#
|
|
# Brings a blank box up to a usable state: users, SSH, networking, firewall,
|
|
# Docker, shell and editor tooling, language runtimes.
|
|
#
|
|
# Run as root: sudo scripts/setup/machine-setup/machine-setup.sh
|
|
# =============================================================================
|
|
|
|
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
|
PROGRESS_FILE="$SCRIPT_DIR/.setup-progress"
|
|
|
|
# Shared state, output helpers, the step/resume machine and OS detection. Kept in
|
|
# lib/ so a step can eventually be read — or run — on its own without dragging the
|
|
# whole script in. Definitions only; nothing in there acts.
|
|
# shellcheck source=lib/base.sh
|
|
source "$SCRIPT_DIR/lib/base.sh"
|
|
# shellcheck source=lib/packages.sh
|
|
source "$SCRIPT_DIR/lib/packages.sh"
|
|
# shellcheck source=lib/tools.sh
|
|
source "$SCRIPT_DIR/lib/tools.sh"
|
|
# shellcheck source=lib/system.sh
|
|
source "$SCRIPT_DIR/lib/system.sh"
|
|
# shellcheck source=lib/disk.sh
|
|
source "$SCRIPT_DIR/lib/disk.sh"
|
|
|
|
# Trap errors with context. Installed here rather than in lib/base.sh, because
|
|
# that file is definitions only and a trap is a side effect on whoever sources it.
|
|
trap 'echo ""; echo -e "${RED}╔══════════════════════════════════════════════════╗${NC}"; echo -e "${RED}║ SETUP FAILED${NC}"; echo -e "${RED}║ Step: ${CURRENT_STEP:-unknown}${NC}"; echo -e "${RED}║ Line: $LINENO${NC}"; echo -e "${RED}║ Command: $BASH_COMMAND${NC}"; echo -e "${RED}╚══════════════════════════════════════════════════╝${NC}"' ERR
|
|
|
|
# =============================================================================
|
|
# 1. Pre-flight
|
|
# =============================================================================
|
|
|
|
echo ""
|
|
echo -e "${BOLD}╔══════════════════════════════════════════════════╗${NC}"
|
|
echo -e "${BOLD}║ Machine Setup ║${NC}"
|
|
echo -e "${BOLD}╚══════════════════════════════════════════════════╝${NC}"
|
|
|
|
detect_os
|
|
echo ""
|
|
info "Machine: ${OS_NAME} (${ARCH})"
|
|
info "Packages: ${PM:-none detected}"
|
|
[[ "$IS_WSL" == true ]] && warn "WSL detected — the suspend, logind and boot-hang steps do not apply here"
|
|
|
|
# Everything below this line is written against apt and systemd. Detection above
|
|
# recognises pacman, dnf and brew so the branches have somewhere to hang, but
|
|
# nothing implements them yet — and running the apt path on Arch would half-build
|
|
# a machine and stop somewhere unhelpful. Refuse clearly instead, and relax this
|
|
# list one entry at a time as each package manager grows a real path.
|
|
case "$PM" in
|
|
apt) ;;
|
|
"") fail "Could not find a package manager for '${OS_NAME}'." ;;
|
|
*) fail "${OS_NAME} uses ${PM}, which this script does not implement yet — apt-based systems only, so far." ;;
|
|
esac
|
|
|
|
ask_machine_role
|
|
info "Role: ${MACHINE_ROLE}"
|
|
|
|
if [[ -f "$PROGRESS_FILE" ]]; then
|
|
DONE_COUNT=$(wc -l < "$PROGRESS_FILE")
|
|
echo -e "${YELLOW} Resuming — $DONE_COUNT step(s) already completed${NC}"
|
|
echo -e "${YELLOW} Progress file: $PROGRESS_FILE${NC}"
|
|
echo -e "${YELLOW} To start fresh: rm $PROGRESS_FILE${NC}"
|
|
fi
|
|
|
|
if [[ "$EUID" -ne 0 ]]; then
|
|
fail "Please run as root: sudo ./machine-setup.sh"
|
|
fi
|
|
|
|
prompt_value USERNAME "New admin username (or existing)" ""
|
|
if [[ -z "$USERNAME" ]]; then
|
|
fail "Username cannot be empty"
|
|
fi
|
|
|
|
USER_HOME="/home/$USERNAME"
|
|
|
|
ask_officer_root
|
|
if [[ -d "$OFFICER_ROOT" ]]; then
|
|
info "Officer: ${OFFICER_ROOT} (exists already)"
|
|
else
|
|
info "Officer: ${OFFICER_ROOT}"
|
|
fi
|
|
|
|
# Always, and outside any step: everything below reads this index — core utils,
|
|
# the fastfetch PPA, the Docker repo — and `step` skips a step whose name is
|
|
# already in the progress file. With the refresh inside one of those, a resumed
|
|
# run installed against whatever the index happened to say hours or days ago.
|
|
echo ""
|
|
info "Refreshing the package index..."
|
|
pkg_refresh >/dev/null
|
|
|
|
# =============================================================================
|
|
# 2. Disk space
|
|
# =============================================================================
|
|
#
|
|
# First of the sections that change anything, because everything after it sizes
|
|
# itself from free disk — the swapfile and the ballast both.
|
|
|
|
step "Disk space"
|
|
if ! skip; then
|
|
ROOT_DEV="$(root_device)"
|
|
ROOT_DISK="$(parent_disk "$ROOT_DEV")"
|
|
ROOT_PART="$(backing_partition "$ROOT_DEV" || true)"
|
|
|
|
DISK_B="$(dev_bytes "$ROOT_DISK")"
|
|
CONT_B="$(dev_bytes "$ROOT_DEV")"
|
|
FS_B="$(fs_bytes "$ROOT_DEV")"
|
|
VG_FREE_B="$(vg_free_bytes)"
|
|
|
|
# A filesystem is always a little smaller than the thing holding it —
|
|
# metadata, journal, reserved blocks. Only a real gap is worth reporting.
|
|
SLACK=$((1024 * 1024 * 1024))
|
|
|
|
echo ""
|
|
info "Disk space — whether the root filesystem is actually using the whole drive"
|
|
echo " Ubuntu's installer, left on its defaults, gives the root volume a"
|
|
echo " fixed size and leaves the rest of the drive unallocated. On a 2TB"
|
|
echo " disk that is a 100G root and no sign anything is wrong: lsblk shows"
|
|
echo " the whole drive, df shows 100G, and the two are never seen together"
|
|
echo " until the day it fills up. Growing a virtual disk at the provider"
|
|
echo " leaves the same shape."
|
|
echo ""
|
|
echo " drive: $(human_bytes "$DISK_B") ${ROOT_DISK}"
|
|
echo " volume: $(human_bytes "$CONT_B") ${ROOT_DEV}"
|
|
echo " filesystem: $(human_bytes "$FS_B") $(root_fstype), mounted at /"
|
|
((VG_FREE_B > SLACK)) && echo " unused in LVM: $(human_bytes "$VG_FREE_B")"
|
|
|
|
# growpart is the authority on whether a partition can move, but installing a
|
|
# package just to ask is too eager — the arithmetic decides whether it is even
|
|
# worth looking.
|
|
MIGHT_GROW=false
|
|
((DISK_B - CONT_B > SLACK)) && MIGHT_GROW=true
|
|
[[ -n "$ROOT_PART" ]] && $MIGHT_GROW && ensure_growpart
|
|
|
|
if ((VG_FREE_B > SLACK)); then
|
|
echo ""
|
|
echo " $(human_bytes "$VG_FREE_B") is sitting unallocated in the volume group"
|
|
echo " the fix is lvextend, then growing the filesystem into it — both online"
|
|
if confirm "Use it?"; then
|
|
grow_lv && grow_fs
|
|
ok "root filesystem is now $(human_bytes "$(fs_bytes "$ROOT_DEV")")"
|
|
SUMMARY+=("Disk: reclaimed $(human_bytes "$VG_FREE_B") from the volume group")
|
|
else
|
|
warn "skipped by request"
|
|
SUMMARY+=("Disk: SKIPPED — $(human_bytes "$VG_FREE_B") left unallocated")
|
|
fi
|
|
|
|
elif [[ -n "$ROOT_PART" ]] && partition_can_grow "$ROOT_PART"; then
|
|
echo ""
|
|
echo " the partition stops short of the end of the drive"
|
|
echo " this is the one step that edits the partition table — it only ever"
|
|
echo " moves the end of ${ROOT_PART} outwards, and never touches another one"
|
|
if confirm "Extend it?"; then
|
|
grow_partition "$ROOT_PART"
|
|
if root_is_lvm; then
|
|
grow_pv "$ROOT_PART"
|
|
grow_lv
|
|
fi
|
|
grow_fs
|
|
ok "root filesystem is now $(human_bytes "$(fs_bytes "$ROOT_DEV")")"
|
|
SUMMARY+=("Disk: partition extended, filesystem now $(human_bytes "$(fs_bytes "$ROOT_DEV")")")
|
|
else
|
|
warn "skipped by request"
|
|
SUMMARY+=("Disk: SKIPPED — partition left short of the drive")
|
|
fi
|
|
|
|
elif ((FS_B > 0 && CONT_B - FS_B > SLACK)); then
|
|
echo ""
|
|
echo " the filesystem is smaller than the volume holding it"
|
|
if confirm "Grow it?"; then
|
|
grow_fs
|
|
ok "root filesystem is now $(human_bytes "$(fs_bytes "$ROOT_DEV")")"
|
|
SUMMARY+=("Disk: filesystem grown to $(human_bytes "$(fs_bytes "$ROOT_DEV")")")
|
|
else
|
|
warn "skipped by request"
|
|
SUMMARY+=("Disk: SKIPPED — filesystem left short of its volume")
|
|
fi
|
|
|
|
else
|
|
echo ""
|
|
echo " the whole drive is in use, nothing to reclaim"
|
|
SUMMARY+=("Disk: already using the whole drive")
|
|
fi
|
|
step_ok
|
|
fi
|
|
|
|
# =============================================================================
|
|
# 3. System update
|
|
# =============================================================================
|
|
#
|
|
# Its own section because it is the only thing in the script that moves versions
|
|
# of software already on the machine. Everything else only ever adds what is
|
|
# absent, so this is the one that deserves to be refused on its own.
|
|
#
|
|
# The index refresh is NOT here — it runs in pre-flight, unconditionally, because
|
|
# every later step reads it and this one can be skipped.
|
|
|
|
step "System update"
|
|
if ! skip; then
|
|
mapfile -t UPGRADABLE < <(pkg_upgradable)
|
|
|
|
echo ""
|
|
info "System update — upgrades installed packages to their latest versions"
|
|
|
|
if ((${#UPGRADABLE[@]} == 0)); then
|
|
echo " to upgrade: nothing, everything is current"
|
|
SUMMARY+=("System update: already up to date")
|
|
else
|
|
echo " to upgrade: ${#UPGRADABLE[@]} package(s)"
|
|
# Capped, because a box that has not been touched in months lists hundreds
|
|
# and a wall of names is no more informative than a count.
|
|
printf ' %s\n' "${UPGRADABLE[@]:0:25}"
|
|
((${#UPGRADABLE[@]} > 25)) && echo " … and $((${#UPGRADABLE[@]} - 25)) more"
|
|
|
|
if confirm "Proceed?"; then
|
|
pkg_upgrade_all
|
|
ok "System upgraded"
|
|
SUMMARY+=("System upgraded: ${#UPGRADABLE[@]} package(s)")
|
|
else
|
|
warn "skipped by request"
|
|
SUMMARY+=("System update: SKIPPED by request — ${#UPGRADABLE[@]} package(s) left as they are")
|
|
fi
|
|
fi
|
|
step_ok
|
|
fi
|
|
|
|
# =============================================================================
|
|
# 4. Core utils
|
|
# =============================================================================
|
|
#
|
|
# What the distribution provides: the six this script would break without, and
|
|
# the command-line tools that make a machine worth sitting at.
|
|
|
|
step "Core utils"
|
|
if ! skip; then
|
|
# shellcheck disable=SC2046 # word splitting is how the list is passed
|
|
pkg_install "Core utils" $(pkgs_core)
|
|
summarise_last "Core utils"
|
|
step_ok
|
|
fi
|
|
|
|
# =============================================================================
|
|
# 5. Command-line tools
|
|
# =============================================================================
|
|
#
|
|
# A different thing from core utils, and kept apart from them: upstream binaries
|
|
# fetched from upstream, on their own release cadence, none of which the
|
|
# distribution ships. Lumping them in made a run look like it was installing
|
|
# system packages and then start pulling tarballs unannounced.
|
|
|
|
step "Command-line tools"
|
|
if ! skip; then
|
|
# shellcheck disable=SC2046 # word splitting is how the list is passed
|
|
tools_install "Command-line tools" $(tools_default)
|
|
summarise_last "Command-line tools"
|
|
step_ok
|
|
fi
|
|
|
|
|
|
# =============================================================================
|
|
# 6. Locale
|
|
# =============================================================================
|
|
#
|
|
# LOCALE in the environment overrides the default.
|
|
|
|
step "Locale"
|
|
if ! skip; then
|
|
LOCALE="${LOCALE:-en_US.UTF-8}"
|
|
CURRENT_LOCALE="$(locale_current)"
|
|
|
|
echo ""
|
|
info "Locale — the system language and character encoding"
|
|
echo " current: ${CURRENT_LOCALE:-none configured}"
|
|
echo " to set: ${LOCALE}"
|
|
|
|
if [[ "$CURRENT_LOCALE" == "$LOCALE" ]] && locale_is_generated "$LOCALE"; then
|
|
echo " already set and generated, nothing to do"
|
|
SUMMARY+=("Locale: already ${LOCALE}")
|
|
else
|
|
# Say which of the two is actually wrong, since they fail differently: a
|
|
# missing LANG means the C locale, a missing generation means every login
|
|
# prints a setlocale warning.
|
|
[[ "$CURRENT_LOCALE" != "$LOCALE" ]] && echo " LANG is not set to it"
|
|
locale_is_generated "$LOCALE" || echo " the locale has not been generated on this machine"
|
|
|
|
if confirm "Proceed?"; then
|
|
locale_set "$LOCALE"
|
|
ok "Locale set to ${LOCALE}"
|
|
SUMMARY+=("Locale: ${LOCALE}")
|
|
else
|
|
warn "skipped by request"
|
|
SUMMARY+=("Locale: SKIPPED by request — left at ${CURRENT_LOCALE:-unset}")
|
|
fi
|
|
fi
|
|
step_ok
|
|
fi
|
|
|
|
# =============================================================================
|
|
# 7. Timezone
|
|
# =============================================================================
|
|
#
|
|
# TIMEZONE in the environment answers the prompt ahead of time.
|
|
|
|
step "Timezone"
|
|
if ! skip; then
|
|
CURRENT_TZ="$(timezone_current)"
|
|
|
|
echo ""
|
|
info "Timezone — what logs, timers and every printed date are relative to"
|
|
echo " current: ${CURRENT_TZ:-unknown}"
|
|
|
|
if [[ -z "${TIMEZONE:-}" ]]; then
|
|
echo ""
|
|
for i in "${!TZ_OPTIONS[@]}"; do
|
|
printf ' [%d] %s\n' "$((i + 1))" "${TZ_OPTIONS[$i]}"
|
|
done
|
|
echo ""
|
|
|
|
while [[ -z "${TIMEZONE:-}" ]]; do
|
|
if ! read -rp " Pick a number, or type a zone name — Enter keeps ${CURRENT_TZ:-the current one}: " TZ_CHOICE; then
|
|
echo ""
|
|
fail "No answer. Set TIMEZONE=<zone> to answer this ahead of time."
|
|
fi
|
|
|
|
if [[ -z "$TZ_CHOICE" ]]; then
|
|
TIMEZONE="$CURRENT_TZ"
|
|
elif [[ "$TZ_CHOICE" =~ ^[0-9]+$ ]]; then
|
|
if ((TZ_CHOICE >= 1 && TZ_CHOICE <= ${#TZ_OPTIONS[@]})); then
|
|
TIMEZONE="${TZ_OPTIONS[$((TZ_CHOICE - 1))]}"
|
|
else
|
|
warn "There is no option ${TZ_CHOICE}."
|
|
fi
|
|
else
|
|
# Validated here rather than left to timedatectl, which fails on an
|
|
# unknown name and would take the whole run down over a typo.
|
|
if timezone_is_valid "$TZ_CHOICE"; then
|
|
TIMEZONE="$TZ_CHOICE"
|
|
else
|
|
warn "Not a zone this machine knows: '${TZ_CHOICE}' — try e.g. Europe/Berlin"
|
|
fi
|
|
fi
|
|
done
|
|
elif ! timezone_is_valid "$TIMEZONE"; then
|
|
fail "TIMEZONE='${TIMEZONE}' is not a zone this machine knows."
|
|
fi
|
|
|
|
if [[ "$TIMEZONE" == "$CURRENT_TZ" ]]; then
|
|
echo " keeping ${CURRENT_TZ}, nothing to do"
|
|
SUMMARY+=("Timezone: already ${CURRENT_TZ}")
|
|
else
|
|
echo " to set: ${TIMEZONE}"
|
|
if confirm "Proceed?"; then
|
|
timezone_set "$TIMEZONE"
|
|
ok "Timezone set to ${TIMEZONE}"
|
|
SUMMARY+=("Timezone: ${TIMEZONE}")
|
|
else
|
|
warn "skipped by request"
|
|
SUMMARY+=("Timezone: SKIPPED by request — left at ${CURRENT_TZ:-unknown}")
|
|
fi
|
|
fi
|
|
step_ok
|
|
fi
|
|
|
|
# =============================================================================
|
|
# 8. Swap
|
|
# =============================================================================
|
|
#
|
|
# Disk the kernel can park cold pages on when RAM fills, so a spike costs
|
|
# latency instead of a process. A `bun install` or a Docker build on a small
|
|
# machine is exactly the spike this is for.
|
|
|
|
step "Swap"
|
|
if ! skip; then
|
|
ACTIVE_SWAP_GB="$(swap_active_gb)"
|
|
WANT_SWAP_GB="$(swap_recommended_gb)"
|
|
SWAPPINESS="$(swappiness_for_role)"
|
|
CURRENT_SWAPPINESS="$(sysctl -n vm.swappiness 2>/dev/null || echo unknown)"
|
|
|
|
echo ""
|
|
info "Swap — overflow space so a memory spike costs speed rather than a process"
|
|
echo " RAM: $(ram_gb)G"
|
|
echo " active swap: ${ACTIVE_SWAP_GB}G"
|
|
echo " swappiness: ${CURRENT_SWAPPINESS} -> ${SWAPPINESS} (${MACHINE_ROLE})"
|
|
|
|
if [[ "$IS_WSL" == true ]]; then
|
|
# WSL2 runs its own managed swap inside the VM; a swapfile here is wasted
|
|
# disk and is not what the kernel would use anyway.
|
|
echo " WSL manages its own swap — leaving it alone"
|
|
SUMMARY+=("Swap: left to WSL")
|
|
elif ((ACTIVE_SWAP_GB > 0)); then
|
|
echo " already has ${ACTIVE_SWAP_GB}G of swap, leaving it alone"
|
|
if [[ "$CURRENT_SWAPPINESS" != "$SWAPPINESS" ]] && confirm "Set swappiness to ${SWAPPINESS}?"; then
|
|
swappiness_set "$SWAPPINESS"
|
|
ok "swappiness set to ${SWAPPINESS}"
|
|
SUMMARY+=("Swap: kept ${ACTIVE_SWAP_GB}G, swappiness ${SWAPPINESS}")
|
|
else
|
|
SUMMARY+=("Swap: kept ${ACTIVE_SWAP_GB}G")
|
|
fi
|
|
elif ((WANT_SWAP_GB == 0)); then
|
|
# Capped to nothing by the disk check rather than by choice.
|
|
warn "not enough free disk to add swap safely — $(disk_free_gb)G free"
|
|
SUMMARY+=("Swap: none added, disk too full")
|
|
else
|
|
echo " to create: ${WANT_SWAP_GB}G at ${SWAPFILE} ($(disk_free_gb)G free now)"
|
|
if confirm "Proceed?"; then
|
|
swap_create "$WANT_SWAP_GB"
|
|
swappiness_set "$SWAPPINESS"
|
|
ok "${WANT_SWAP_GB}G swap active, swappiness ${SWAPPINESS}"
|
|
SUMMARY+=("Swap: ${WANT_SWAP_GB}G created, swappiness ${SWAPPINESS}")
|
|
else
|
|
warn "skipped by request"
|
|
SUMMARY+=("Swap: SKIPPED by request")
|
|
fi
|
|
fi
|
|
step_ok
|
|
fi
|
|
|
|
# =============================================================================
|
|
# 9. Emergency disk ballast
|
|
# =============================================================================
|
|
#
|
|
# Always offered, whatever the role — the role only decides which way the
|
|
# recommendation points.
|
|
|
|
step "Emergency disk ballast"
|
|
# Servers only. On a machine you sit at, the disk filling up announces itself —
|
|
# the editor refuses to save, the browser complains — and you are there to deal
|
|
# with it. The reserve is for the box nobody is watching, where the first sign is
|
|
# a service that stopped working hours ago. Skipped rather than offered, but said
|
|
# out loud, so a silent gap in the run is never left unexplained.
|
|
if ! skip && ! is_server; then
|
|
echo ""
|
|
info "Emergency disk ballast — not offered on a ${MACHINE_ROLE} machine"
|
|
echo " The reserve is for a box nobody is watching. You are sitting at"
|
|
echo " this one, so a filling disk tells you itself."
|
|
SUMMARY+=("Disk ballast: not applicable on ${MACHINE_ROLE}")
|
|
step_ok
|
|
elif ! skip; then
|
|
echo ""
|
|
info "Emergency disk ballast — a reserve you can burn when the disk fills up"
|
|
echo " A file holding nothing, whose only job is to be deleted. A root cron"
|
|
echo " checks every 10 minutes and removes it if free space drops below"
|
|
echo " ${BALLAST_THRESHOLD}%, which buys you room to log in and clean up rather than"
|
|
echo " meeting a wedged machine — Docker, journald and postgres all"
|
|
echo " misbehave badly at 100% full, and not all of them recover on their"
|
|
echo " own."
|
|
echo ""
|
|
echo " It is a one-shot valve: once spent, run this again to recreate it."
|
|
|
|
if [[ -f "${USER_HOME}/${BALLAST_NAME}" ]]; then BALLAST_FILE="${USER_HOME}/${BALLAST_NAME}"; fi
|
|
[[ -f "${OFFICER_ROOT}/${BALLAST_NAME}" ]] && BALLAST_FILE="${OFFICER_ROOT}/${BALLAST_NAME}"
|
|
|
|
if ballast_exists; then
|
|
echo ""
|
|
echo " already present: $(ballast_size_human) at ${BALLAST_FILE}"
|
|
SUMMARY+=("Disk ballast: already present ($(ballast_size_human))")
|
|
elif ! confirm "Create one?"; then
|
|
warn "skipped by request"
|
|
SUMMARY+=("Disk ballast: SKIPPED by request")
|
|
else
|
|
# ── where ──
|
|
#
|
|
# A ballast only protects the filesystem it sits on, because the checker
|
|
# measures its own directory. So this is also a choice of which mount is
|
|
# being protected, not just where the file is tidiest.
|
|
echo ""
|
|
info "Where should it go?"
|
|
echo " [1] ${USER_HOME}/${BALLAST_NAME}"
|
|
echo " your home — easiest to find again months from now"
|
|
echo " [2] ${OFFICER_ROOT}/${BALLAST_NAME}"
|
|
echo " beside Officer — same place as everything else it owns"
|
|
echo " [3] somewhere else, typed in"
|
|
echo ""
|
|
|
|
BALLAST_FILE=""
|
|
while [[ -z "$BALLAST_FILE" ]]; do
|
|
if ! read -rp " Which one? (1/2/3) [1]: " BALLAST_WHERE; then
|
|
echo ""
|
|
fail "No answer."
|
|
fi
|
|
case "${BALLAST_WHERE:-1}" in
|
|
1) BALLAST_FILE="${USER_HOME}/${BALLAST_NAME}" ;;
|
|
2) BALLAST_FILE="${OFFICER_ROOT}/${BALLAST_NAME}" ;;
|
|
3)
|
|
read -rp " Full path to the file: " BALLAST_TYPED || fail "No answer."
|
|
BALLAST_TYPED="${BALLAST_TYPED/#\~/$USER_HOME}"
|
|
if [[ "$BALLAST_TYPED" == /* ]]; then
|
|
BALLAST_FILE="$BALLAST_TYPED"
|
|
else
|
|
warn "That needs to be an absolute path, starting with /"
|
|
fi
|
|
;;
|
|
*) warn "Pick 1, 2 or 3." ;;
|
|
esac
|
|
done
|
|
|
|
# ── how much ──
|
|
#
|
|
# Percentages mean nothing without the numbers behind them, and the number
|
|
# that matters is what is LEFT — the point of the reserve is to be big enough
|
|
# to matter and small enough not to be the thing that filled the disk.
|
|
BALLAST_FREE_KB="$(ballast_free_kb "$(dirname "$BALLAST_FILE")")"
|
|
|
|
echo ""
|
|
info "How much? ${BALLAST_FILE} sits on a filesystem with $(human_bytes $((BALLAST_FREE_KB * 1024))) free."
|
|
for i in 1 2 3; do
|
|
case $i in
|
|
1) BP=5 ;;
|
|
2) BP=10 ;;
|
|
3) BP=20 ;;
|
|
esac
|
|
BSZ=$((BALLAST_FREE_KB * BP / 100))
|
|
printf ' [%d] %3d%% — reserves %-8s leaving %s free\n' \
|
|
"$i" "$BP" "$(human_bytes $((BSZ * 1024)))" "$(human_bytes $(((BALLAST_FREE_KB - BSZ) * 1024)))"
|
|
done
|
|
echo ""
|
|
|
|
BALLAST_PCT=""
|
|
while [[ -z "$BALLAST_PCT" ]]; do
|
|
if ! read -rp " Which one? (1/2/3) [2]: " BALLAST_SIZE_CHOICE; then
|
|
echo ""
|
|
fail "No answer."
|
|
fi
|
|
case "${BALLAST_SIZE_CHOICE:-2}" in
|
|
1) BALLAST_PCT=5 ;;
|
|
2) BALLAST_PCT=10 ;;
|
|
3) BALLAST_PCT=20 ;;
|
|
*) warn "Pick 1, 2 or 3." ;;
|
|
esac
|
|
done
|
|
|
|
BALLAST_MB=$((BALLAST_FREE_KB * BALLAST_PCT / 100 / 1024))
|
|
ballast_create "$BALLAST_MB"
|
|
ballast_install_checker
|
|
ok "ballast $(ballast_size_human) at ${BALLAST_FILE}, checked every 10 minutes"
|
|
ok "status any time: ${BALLAST_CHECKER} --status"
|
|
SUMMARY+=("Disk ballast: $(ballast_size_human) at ${BALLAST_FILE} (${BALLAST_PCT}%)")
|
|
fi
|
|
step_ok
|
|
fi
|
|
|
|
# =============================================================================
|
|
# 10. earlyoom
|
|
# =============================================================================
|
|
|
|
step "earlyoom"
|
|
if ! skip; then
|
|
echo ""
|
|
info "earlyoom — keeps the machine reachable when it runs out of memory"
|
|
echo " The kernel's own OOM killer waits until an allocation actually"
|
|
echo " fails, and by then the machine has usually spent minutes thrashing:"
|
|
echo " unresponsive, ssh refusing to connect, nothing to do but reset it."
|
|
echo " earlyoom watches free memory and kills the biggest consumer while"
|
|
echo " there is still enough left to stay logged in."
|
|
echo ""
|
|
echo " This is what happens after swap runs out, so the two go together."
|
|
|
|
if earlyoom_is_active; then
|
|
echo " already installed and running"
|
|
SUMMARY+=("earlyoom: already running")
|
|
elif confirm "Install it?"; then
|
|
earlyoom_install
|
|
if earlyoom_is_active; then
|
|
ok "earlyoom running"
|
|
SUMMARY+=("earlyoom: installed and running")
|
|
else
|
|
warn "earlyoom installed but not running — check: systemctl status earlyoom"
|
|
SUMMARY+=("earlyoom: installed, not running")
|
|
fi
|
|
else
|
|
warn "skipped by request"
|
|
SUMMARY+=("earlyoom: SKIPPED by request")
|
|
fi
|
|
step_ok
|
|
fi
|
|
|
|
# =============================================================================
|
|
# 11. inotify watch limit
|
|
# =============================================================================
|
|
|
|
step "inotify watch limit"
|
|
if ! skip; then
|
|
CURRENT_WATCHES="$(inotify_current_watches)"
|
|
|
|
echo ""
|
|
info "inotify watch limit — how many files can be watched for changes at once"
|
|
echo " A single file watcher walking a project with node_modules in it can"
|
|
echo " exhaust the stock limit on its own, and every watcher on the machine"
|
|
echo " draws from the same pool. The failure is silent: nothing errors, the"
|
|
echo " watcher just stops noticing changes. Hot reload goes quiet, a build"
|
|
echo " stops rebuilding, and the reason is never on screen."
|
|
echo ""
|
|
echo " current: ${CURRENT_WATCHES}"
|
|
echo " to set: ${INOTIFY_WATCHES}"
|
|
if is_role dev; then
|
|
echo " recommended on dev — editors, bun --watch and vite are all watchers"
|
|
else
|
|
echo " less pressing on ${MACHINE_ROLE}, but anything running bun --watch or"
|
|
echo " serving a file browser is a watcher too"
|
|
fi
|
|
|
|
if ((CURRENT_WATCHES >= INOTIFY_WATCHES)); then
|
|
echo " already at or above that, nothing to do"
|
|
SUMMARY+=("inotify watches: already ${CURRENT_WATCHES}")
|
|
elif confirm "Raise it?"; then
|
|
inotify_raise
|
|
ok "inotify watches raised to $(inotify_current_watches)"
|
|
SUMMARY+=("inotify watches: raised to ${INOTIFY_WATCHES}")
|
|
else
|
|
warn "skipped by request"
|
|
SUMMARY+=("inotify watches: SKIPPED by request — left at ${CURRENT_WATCHES}")
|
|
fi
|
|
step_ok
|
|
fi
|
|
|
|
# =============================================================================
|
|
# NOT PORTED YET
|
|
# =============================================================================
|
|
#
|
|
# Sections still to move across from scripts/setup-old/setup-ubuntu.sh, in order:
|
|
#
|
|
# auto-suspend · boot-hang fix · user creation ·
|
|
# ssh keys · ssh hardening · dns · static ip · fail2ban · unattended-upgrades ·
|
|
# git config · docker · zsh + prompt · tailscale · neovim · js runtimes ·
|
|
# dev tools · ufw · zshrc
|
|
#
|
|
# Each arrives as its own commit. Delete this block when the list is empty.
|
|
|
|
|
|
# =============================================================================
|
|
# 12. Summary
|
|
# =============================================================================
|
|
|
|
echo ""
|
|
echo ""
|
|
if [[ ${#ERRORS[@]} -gt 0 ]]; then
|
|
echo -e "${YELLOW}╔══════════════════════════════════════════════════╗${NC}"
|
|
echo -e "${YELLOW}║ Setup Complete (with warnings) ║${NC}"
|
|
echo -e "${YELLOW}╚══════════════════════════════════════════════════╝${NC}"
|
|
else
|
|
echo -e "${GREEN}╔══════════════════════════════════════════════════╗${NC}"
|
|
echo -e "${GREEN}║ Setup Complete ║${NC}"
|
|
echo -e "${GREEN}╚══════════════════════════════════════════════════╝${NC}"
|
|
fi
|
|
|
|
echo ""
|
|
echo -e "${BOLD} What was done:${NC}"
|
|
for item in "${SUMMARY[@]}"; do
|
|
echo -e " ${GREEN}+${NC} $item"
|
|
done
|
|
|
|
if [[ ${#ERRORS[@]} -gt 0 ]]; then
|
|
echo ""
|
|
echo -e "${BOLD} Non-critical issues:${NC}"
|
|
for err in "${ERRORS[@]}"; do
|
|
echo -e " ${YELLOW}!${NC} $err"
|
|
done
|
|
fi
|
|
|
|
echo ""
|
|
echo -e "${BOLD} Machine:${NC}"
|
|
echo " System: $OS_NAME ($ARCH)"
|
|
echo " Role: $MACHINE_ROLE"
|
|
echo " User: $USERNAME"
|
|
echo " Home: $USER_HOME"
|
|
echo " Officer: $OFFICER_ROOT"
|
|
[[ -n "${TS_IP:-}" && "$TS_IP" != "unknown" ]] && echo " Tailscale: $TS_IP"
|
|
echo ""
|
|
|
|
# Clean up progress file on success
|
|
rm -f "$PROGRESS_FILE"
|