[Unit]
Description=left4me server instance %i
After=network-online.target
Wants=network-online.target
# Bound the restart loop. Without these, a persistent ExecStartPre or
# ExecStart failure spins indefinitely. Note: these are [Unit]-section
# directives (systemd 230+), not [Service].
StartLimitBurst=5
StartLimitIntervalSec=60s

[Service]
Type=simple
User=left4me
Group=left4me
EnvironmentFile=/etc/left4me/host.env
EnvironmentFile=/var/lib/left4me/instances/%i/instance.env
# `-` prefix: chdir failure is non-fatal. systemd applies WorkingDirectory
# before every Exec line — including ExecStartPre — but the merged dir only
# exists once ExecStartPre's overlay mount succeeds. With `-`, ExecStartPre
# runs in the unit's home (cwd doesn't matter for the mount helper); the
# ExecStart re-applies WorkingDirectory after the mount and finds the dir.
WorkingDirectory=-/var/lib/left4me/runtime/%i/merged/left4dead2
# Single source of truth for the kernel-overlayfs mount lifecycle: the web
# app's start_instance only stages cfg files and asks systemd to enable+
# start this unit; the actual `mount -t overlay` lives here so reboot
# auto-start works the same as a UI-driven start. ExecStopPost mirrors it
# so the unmount lives in the same place — no Python-side _mounter needed
# in stop/delete/reset paths. Both helper verbs are idempotent.
#
# `+` prefix runs the helper as PID 1 (root, no sandbox). Required because
# the unit has NoNewPrivileges=true, which blocks sudo's setuid escalation
# — and the helper itself needs root for the mount/umount syscalls.
#
# `nsenter --mount=/proc/1/ns/mnt --` runs the helper Python interpreter
# in PID 1's mount namespace. Without this, the `+` prefix removes the
# sandbox/credentials but does NOT detach from the unit's per-service
# mount namespace (created by PrivateTmp/Protect*) — so the helper
# process itself would hold a reference to that namespace, keeping the
# slave-mount tree alive after the cgroup empties, and umount in PID 1
# would return EBUSY for as long as the helper ran. Putting nsenter at
# the unit-level (as opposed to inside the helper, where only the
# umount syscall escaped) is what actually frees the namespace. Once
# the helper is in PID 1's namespace, ExecStopPost's umount succeeds
# on the first try with no retry/race window. ExecStopPost (not
# ExecStop) so unmount runs after the cgroup is cleared; ExecStop runs
# while srcds is still alive and would EBUSY.
ExecStartPre=+/usr/bin/nsenter --mount=/proc/1/ns/mnt -- /usr/local/libexec/left4me/left4me-overlay mount %i
# Run from the merged overlay, NOT installation/. srcds_run is a shell
# script that `cd`s to its own dirname before exec'ing srcds_linux, so the
# binary's path determines where the engine reads gameinfo.txt and addons
# from — WorkingDirectory has no effect. Invoking installation/srcds_run
# would resolve everything against the lower layer and never see overlay-
# provided plugins (Metamod/SourceMod) or cfgs (zonemod, confogl).
ExecStart=/var/lib/left4me/runtime/%i/merged/srcds_run -game left4dead2 +hostport ${L4D2_PORT} $L4D2_ARGS
ExecStopPost=+/usr/bin/nsenter --mount=/proc/1/ns/mnt -- /usr/local/libexec/left4me/left4me-overlay umount %i
Restart=on-failure
RestartSec=5

# Resource control baseline — see docs/superpowers/specs/2026-05-09-l4d2-server-host-perf-baseline-design.md
Slice=l4d2-game.slice
Nice=-5
IOSchedulingClass=best-effort
IOSchedulingPriority=4
OOMScoreAdjust=-200
MemoryHigh=1.5G
MemoryMax=2G
TasksMax=256
LimitNOFILE=65536
KillSignal=SIGINT
TimeoutStopSec=15s
LogRateLimitIntervalSec=0

# Hardening (unchanged from previous baseline).
NoNewPrivileges=true
PrivateTmp=true
PrivateDevices=true
ProtectHome=true
ProtectSystem=strict
ReadOnlyPaths=/var/lib/left4me/installation /var/lib/left4me/overlays
ReadWritePaths=/var/lib/left4me/runtime/%i
RestrictSUIDSGID=true
LockPersonality=true

[Install]
WantedBy=multi-user.target