#!/bin/sh
# Install or remove the OpenFUT systemd supervision set for one environment.
#
# Environments are symmetric on purpose: staging and production differ only in
# unit prefix, anchor container and EnvironmentFile location, so what staging
# proved is what production gets.
#
#   install   copy units, daemon-reload, enable (does NOT start)
#   start     start in dependency order and report the namespace agreement
#   status    one-screen health: units, anchor, netns agreement, mounts
#   uninstall disable + stop + remove units (leaves binaries, DB and env alone)
#
# The install step deliberately does NOT start anything: on production the
# changeover has to be sequenced against retiring the existing detached
# processes, which is an operator decision, not a script's.
#
# usage: openfut-supervision-install.sh <install|start|status|uninstall> <staging|production>
set -eu

ACTION="${1:?install|start|status|uninstall}"
ENVNAME="${2:?staging|production}"
HERE="$(cd "$(dirname "$0")" && pwd)"

case "$ENVNAME" in
  staging)
    PREFIX="openfut-staging"
    ANCHOR="openfut-staging-anchor"
    NSNAME="openfut-staging"
    UNITS="openfut-staging-netns.service openfut-staging-core.service openfut-staging-host.service openfut-staging-netns-reconcile.service openfut-staging-netns-reconcile.timer"
    ENABLE="openfut-staging-netns.service openfut-staging-core.service openfut-staging-host.service openfut-staging-netns-reconcile.timer"
    ;;
  production)
    PREFIX="openfut"
    ANCHOR="openfut-fut-backend"
    NSNAME="openfut"
    UNITS="openfut-netns.service openfut-core.service openfut-host.service openfut-netns-reconcile.service openfut-netns-reconcile.timer"
    ENABLE="openfut-netns.service openfut-core.service openfut-host.service openfut-netns-reconcile.timer"
    ;;
  *) echo "unknown environment '$ENVNAME'" >&2; exit 2 ;;
esac

case "$ACTION" in
  install)
    for u in $UNITS; do
        [ -f "$HERE/$u" ] || { echo "missing unit $HERE/$u" >&2; exit 1; }
        install -m 0644 "$HERE/$u" "/etc/systemd/system/$u"
        echo "installed /etc/systemd/system/$u"
    done
    systemctl daemon-reload
    for u in $UNITS; do systemd-analyze verify "/etc/systemd/system/$u" || true; done
    # shellcheck disable=SC2086
    systemctl enable $ENABLE
    echo "enabled (NOT started — start explicitly once the old processes are retired)"
    ;;

  start)
    systemctl start "${PREFIX}-netns.service"
    systemctl start "${PREFIX}-core.service"
    systemctl start "${PREFIX}-host.service"
    systemctl start "${PREFIX}-netns-reconcile.timer"
    sleep 3
    "$0" status "$ENVNAME"
    ;;

  status)
    printf '%-42s %s\n' "unit" "state"
    for u in $UNITS; do printf '  %-40s %s\n' "$u" "$(systemctl is-active "$u" 2>/dev/null || true)"; done
    cpid="$(docker inspect -f '{{.State.Pid}}' "$ANCHOR" 2>/dev/null || echo 0)"
    if [ "$cpid" != "0" ] && [ -e "/proc/$cpid/ns/net" ]; then
        want="$(readlink "/proc/$cpid/ns/net")"
    else
        want="(anchor absent)"
    fi
    echo "  anchor $ANCHOR pid=$cpid ns=$want"
    for u in "${PREFIX}-core.service" "${PREFIX}-host.service"; do
        mp="$(systemctl show -p MainPID --value "$u" 2>/dev/null || echo 0)"
        ns="-"; [ "$mp" != "0" ] && [ -e "/proc/$mp/ns/net" ] && ns="$(readlink "/proc/$mp/ns/net")"
        match="MISMATCH"; [ "$ns" = "$want" ] && match="ok"
        printf '  %-40s pid=%-8s ns=%-18s %s\n' "$u" "$mp" "$ns" "$match"
    done
    echo "  netns mounts on /run/netns/$NSNAME: $(grep -c "run/netns/$NSNAME" /proc/mounts || true) (1 = healthy, >1 = leaked stack)"
    ;;

  uninstall)
    # shellcheck disable=SC2086
    systemctl disable --now $ENABLE 2>/dev/null || true
    systemctl stop "${PREFIX}-netns-reconcile.service" 2>/dev/null || true
    for u in $UNITS; do rm -f "/etc/systemd/system/$u"; echo "removed /etc/systemd/system/$u"; done
    systemctl daemon-reload
    systemctl reset-failed 2>/dev/null || true
    # The bind mount is intentionally left: the namespace belongs to the
    # container, and tearing it down is not part of removing supervision.
    echo "uninstalled. Binaries, EnvironmentFiles, /run/netns and the database are untouched."
    ;;

  *) echo "unknown action '$ACTION'" >&2; exit 2 ;;
esac