serving-mode: headless / multi-user toggle to free unified memory for vLLM
Flip a DGX Spark (or any Ubuntu box) between its desktop state and a headless inference-serving state — multi-user.target with the desktop + maintenance services pared back — handing the unified 128 GB's desktop overhead (~10-15 GB) back to the GPU KV cache. Companion to Entrpi/qwen3.5-122B-A10B-on-spark. - serving-mode: on / serve / off / status (persists across reboots) - serving-mode.conf.example: optional site config (GPU sidecars / model unit) - examples/vllm-model.service: run the vLLM container under systemd
This commit is contained in:
Entrpi
Executable
+215
@@ -0,0 +1,215 @@
|
||||
#!/usr/bin/env bash
|
||||
# serving-mode — toggle a DGX Spark (or any Ubuntu box) between its full desktop
|
||||
# state, a pared-down ssh-only state, and a headless inference-SERVING state.
|
||||
#
|
||||
# Why: the DGX Spark has 128 GB of UNIFIED memory shared between the OS/desktop
|
||||
# and the GPU. The GNOME desktop, snap/maintenance daemons, and assorted timers
|
||||
# can hold ~10-15 GB that would otherwise be available to the vLLM KV cache.
|
||||
# Dropping to multi-user.target (no GUI) and paring back desktop/maintenance
|
||||
# services hands that memory back to the model — directly raising the KV pool /
|
||||
# usable context length.
|
||||
#
|
||||
# sudo ~/bin/serving-mode on [-u] pared down: multi-user target, desktop /
|
||||
# maintenance services and timers off
|
||||
# (INCLUDING docker); -u also stops+disables
|
||||
# YOUR user units (see serving-mode.conf).
|
||||
# sudo ~/bin/serving-mode serve headless SERVE: multi-user target, desktop /
|
||||
# maintenance off, but DOCKER KEPT UP and the
|
||||
# model unit + your user units brought up.
|
||||
# Linger enabled so the stack survives logout/
|
||||
# reboot. Re-enables NO graphical services.
|
||||
# sudo ~/bin/serving-mode off [-u] restore: graphical target, everything back;
|
||||
# -u also re-enables+starts the user units.
|
||||
# ~/bin/serving-mode status show current state incl. user units (no sudo)
|
||||
#
|
||||
# 'on' and 'serve' persist across reboots (set-default multi-user.target).
|
||||
# NEVER touched in any mode: ssh, NetworkManager + systemd-networkd (one of them
|
||||
# owns the SSH link), resolved, timesyncd, udevd, journald, logind, dbus, polkit,
|
||||
# nvidia-persistenced, rasdaemon (ECC/RAS witness under memory pressure),
|
||||
# logrotate, fstrim, getty consoles, user sessions.
|
||||
#
|
||||
# Site config (optional): define your own GPU sidecars / model unit in
|
||||
# ~/.config/serving-mode.conf (see serving-mode.conf.example)
|
||||
# Without it, serving-mode still does the valuable part — pare the desktop and
|
||||
# free unified memory; it just won't manage any user units or a model unit.
|
||||
#
|
||||
# From: https://github.com/Entrpi/qwen3.5-122B-A10B-on-spark (serving recipe)
|
||||
set -u
|
||||
|
||||
# ---- Desktop / maintenance services turned OFF in both 'on' and 'serve'. ----
|
||||
SERVICES=(
|
||||
cups.service cups.socket cups.path cups-browsed.service
|
||||
bluetooth.service
|
||||
avahi-daemon.service avahi-daemon.socket
|
||||
ModemManager.service
|
||||
fwupd.service colord.service upower.service
|
||||
snapd.service snapd.socket snapd.seeded.service
|
||||
nvidia-dcgm.service dgx-dashboard-admin.service
|
||||
lldpd.service smartmontools.service
|
||||
multipathd.service multipathd.socket
|
||||
rsyslog.service cron.service
|
||||
)
|
||||
# Docker/containerd: EXTRANEOUS in 'on' (disabled), but LOAD-BEARING in 'serve'
|
||||
# (the model is served from a container) — kept up there. Restored by 'off'.
|
||||
DOCKER_SERVICES=(docker.service docker.socket containerd.service)
|
||||
TIMERS=(
|
||||
apt-daily.timer apt-daily-upgrade.timer
|
||||
update-notifier-download.timer update-notifier-motd.timer motd-news.timer
|
||||
man-db.timer ua-timer.timer fwupd-refresh.timer anacron.timer
|
||||
sysstat-collect.timer sysstat-summary.timer dpkg-db-backup.timer
|
||||
e2scrub_all.timer systemd-tmpfiles-clean.timer
|
||||
)
|
||||
|
||||
# ---- Site-specific units (overridden by ~/.config/serving-mode.conf) ----
|
||||
# USER_UNITS — your systemd --user units managed by 'on -u' / 'off -u'.
|
||||
# SERVE_USER_UNITS — the user stack brought up by 'serve'.
|
||||
# MODEL_UNIT — system unit that runs the vLLM container (see examples/).
|
||||
# Defaults are EMPTY so the script is useful with no config (desktop paring only).
|
||||
USER_UNITS=()
|
||||
SERVE_USER_UNITS=()
|
||||
MODEL_UNIT=""
|
||||
|
||||
TARGET_USER="${SUDO_USER:-$USER}"
|
||||
TARGET_UID="$(id -u "$TARGET_USER")"
|
||||
TARGET_HOME="$(getent passwd "$TARGET_USER" | cut -d: -f6)"
|
||||
CONF="${SERVING_MODE_CONF:-$TARGET_HOME/.config/serving-mode.conf}"
|
||||
# shellcheck disable=SC1090
|
||||
[ -f "$CONF" ] && source "$CONF"
|
||||
|
||||
mem() { awk '/MemAvailable/{printf "%.1f GB", $2/1048576}' /proc/meminfo; }
|
||||
need_root() { [ "$(id -u)" = 0 ] || { echo "run: sudo $0 ${1:-}"; exit 1; }; }
|
||||
|
||||
# Run systemctl --user as the target user (works from root via runuser, and
|
||||
# directly when invoked unprivileged).
|
||||
uctl() {
|
||||
if [ "$(id -u)" = 0 ]; then
|
||||
runuser -u "$TARGET_USER" -- env "XDG_RUNTIME_DIR=/run/user/$TARGET_UID" \
|
||||
"DBUS_SESSION_BUS_ADDRESS=unix:path=/run/user/$TARGET_UID/bus" \
|
||||
systemctl --user "$@"
|
||||
else
|
||||
systemctl --user "$@"
|
||||
fi
|
||||
}
|
||||
|
||||
USER_FLAG=0
|
||||
{ [ "${2:-}" = "-u" ] || [ "${2:-}" = "--user" ]; } && USER_FLAG=1
|
||||
|
||||
case "${1:-}" in
|
||||
on)
|
||||
need_root on
|
||||
echo "MemAvailable before: $(mem)"
|
||||
systemctl set-default multi-user.target >/dev/null
|
||||
for u in "${SERVICES[@]}" "${DOCKER_SERVICES[@]}" "${TIMERS[@]}"; do
|
||||
systemctl disable --now "$u" >/dev/null 2>&1
|
||||
done
|
||||
systemctl mask unattended-upgrades.service >/dev/null 2>&1
|
||||
# Wi-Fi supplicant: only stop it if no wifi link is currently active.
|
||||
if nmcli -t -f TYPE,STATE d 2>/dev/null | grep -q '^wifi:connected'; then
|
||||
echo "NOTE: wifi link active -> wpa_supplicant left running"
|
||||
else
|
||||
systemctl disable --now wpa_supplicant.service >/dev/null 2>&1
|
||||
fi
|
||||
if [ "$USER_FLAG" = 1 ] && [ "${#USER_UNITS[@]}" -gt 0 ]; then
|
||||
for uu in "${USER_UNITS[@]}"; do
|
||||
uctl disable --now "$uu" >/dev/null 2>&1
|
||||
done
|
||||
echo "user units stopped+disabled: ${USER_UNITS[*]}"
|
||||
fi
|
||||
systemctl isolate multi-user.target
|
||||
sleep 2
|
||||
echo "MemAvailable after: $(mem)"
|
||||
echo "serving mode ON (persists across reboots; restore: sudo $0 off${USER_FLAG:+ -u})"
|
||||
;;
|
||||
serve)
|
||||
need_root serve
|
||||
echo "MemAvailable before: $(mem)"
|
||||
systemctl set-default multi-user.target >/dev/null
|
||||
# Pare down desktop/maintenance, but DO NOT touch docker here.
|
||||
for u in "${SERVICES[@]}" "${TIMERS[@]}"; do
|
||||
systemctl disable --now "$u" >/dev/null 2>&1
|
||||
done
|
||||
systemctl mask unattended-upgrades.service >/dev/null 2>&1
|
||||
if nmcli -t -f TYPE,STATE d 2>/dev/null | grep -q '^wifi:connected'; then
|
||||
echo "NOTE: wifi link active -> wpa_supplicant left running"
|
||||
else
|
||||
systemctl disable --now wpa_supplicant.service >/dev/null 2>&1
|
||||
fi
|
||||
# Docker is load-bearing for serving: ensure it is enabled and running.
|
||||
for u in "${DOCKER_SERVICES[@]}"; do
|
||||
systemctl enable --now "$u" >/dev/null 2>&1
|
||||
done
|
||||
echo "docker kept up: $(systemctl is-active docker.service 2>/dev/null)"
|
||||
# Let user units run headless without an active login session.
|
||||
loginctl enable-linger "$TARGET_USER" >/dev/null 2>&1
|
||||
# Bring up the user stack (agent + GPU sidecars), if any configured.
|
||||
if [ "${#SERVE_USER_UNITS[@]}" -gt 0 ]; then
|
||||
for uu in "${SERVE_USER_UNITS[@]}"; do
|
||||
uctl enable --now "$uu" >/dev/null 2>&1
|
||||
done
|
||||
echo "user units up: ${SERVE_USER_UNITS[*]}"
|
||||
fi
|
||||
# Bring up the model server if its unit is installed.
|
||||
if [ -n "$MODEL_UNIT" ] && systemctl cat "$MODEL_UNIT" >/dev/null 2>&1; then
|
||||
systemctl enable --now "$MODEL_UNIT" >/dev/null 2>&1
|
||||
echo "model unit started: $MODEL_UNIT ($(systemctl is-active "$MODEL_UNIT" 2>/dev/null))"
|
||||
else
|
||||
echo "NOTE: model unit '${MODEL_UNIT:-<none>}' not installed — model not auto-started"
|
||||
echo " (install examples/vllm-model.service and set MODEL_UNIT in the conf)"
|
||||
fi
|
||||
systemctl isolate multi-user.target
|
||||
sleep 2
|
||||
echo "MemAvailable after: $(mem)"
|
||||
echo "SERVE mode ON (docker up; model+user units up; persists across reboots; restore: sudo $0 off)"
|
||||
;;
|
||||
off)
|
||||
need_root off
|
||||
systemctl unmask unattended-upgrades.service >/dev/null 2>&1
|
||||
for u in "${SERVICES[@]}" "${DOCKER_SERVICES[@]}"; do
|
||||
systemctl enable --now "$u" >/dev/null 2>&1
|
||||
done
|
||||
for t in "${TIMERS[@]}"; do
|
||||
systemctl enable "$t" >/dev/null 2>&1
|
||||
done
|
||||
systemctl enable --now wpa_supplicant.service >/dev/null 2>&1
|
||||
if [ "$USER_FLAG" = 1 ] && [ "${#USER_UNITS[@]}" -gt 0 ]; then
|
||||
for uu in "${USER_UNITS[@]}"; do
|
||||
uctl enable --now "$uu" >/dev/null 2>&1
|
||||
done
|
||||
echo "user units re-enabled+started: ${USER_UNITS[*]}"
|
||||
fi
|
||||
systemctl set-default graphical.target >/dev/null
|
||||
systemctl isolate graphical.target
|
||||
echo "default state restored (graphical target, services + timers re-enabled)"
|
||||
echo "NOTE: 'off' enables the FULL managed list, including anything you had"
|
||||
echo " manually disabled before serving-mode ever ran."
|
||||
;;
|
||||
status)
|
||||
echo "default target : $(systemctl get-default)"
|
||||
echo "MemAvailable : $(mem)"
|
||||
echo "docker : $(systemctl is-active docker.service 2>/dev/null)"
|
||||
echo "linger ($TARGET_USER) : $(loginctl show-user "$TARGET_USER" -p Linger --value 2>/dev/null)"
|
||||
run=0; stop=0
|
||||
for u in "${SERVICES[@]}"; do
|
||||
if systemctl is-active --quiet "$u" 2>/dev/null; then run=$((run+1)); else stop=$((stop+1)); fi
|
||||
done
|
||||
echo "managed services: $run running / $stop stopped"
|
||||
if systemctl is-active --quiet gdm3 2>/dev/null || systemctl is-active --quiet gdm 2>/dev/null; then
|
||||
echo "display manager : running"
|
||||
else
|
||||
echo "display manager : stopped"
|
||||
fi
|
||||
if [ -n "$MODEL_UNIT" ] && systemctl cat "$MODEL_UNIT" >/dev/null 2>&1; then
|
||||
echo "model unit : $MODEL_UNIT = $(systemctl is-active "$MODEL_UNIT" 2>/dev/null)"
|
||||
else
|
||||
echo "model unit : ${MODEL_UNIT:-<none>} = not-installed"
|
||||
fi
|
||||
for uu in "${SERVE_USER_UNITS[@]}"; do
|
||||
st=$(uctl is-active "$uu" 2>/dev/null); [ -n "$st" ] || st=unknown
|
||||
echo "user unit : $uu = $st"
|
||||
done
|
||||
;;
|
||||
*)
|
||||
echo "usage: sudo $0 on|serve|off (or: $0 status)"
|
||||
exit 1
|
||||
;;
|
||||
esac
|
||||
Reference in New Issue
Block a user