#!{{ bash.location }}/bin/bash
# run program under SIGKILL watchdog
# watcher-sigkill <prog> [<progargs> ...]
#
# if the program terminates with SIGKILL - it is restarted after grace period.
# if the program terminates otherwise - whole process terminates.

if [ "$#" -lt 1 ]; then
    echo "Usage: watcher-sigkill <prog> [<progargs> ...]" 1>&2
    exit 1
fi
prog="$@"

progpid=""
killexit="137"  # = 128 + 9  (exit code of process terminated by SIGKILL)

# make sure to terminate children, when we exit.
# needed for e.g. when `slapos node stop ...` kills us.
trap 'atexit' EXIT
atexit() {
    jobs="$(jobs -p)"
    test -n "$jobs" && kill $jobs
}

# run prog under monitoring
while true; do
    echo "run $prog"
    $prog &
    progpid=$!
    echo "wait $progpid"
    wait $progpid
    status=$?
    echo "-> $status"

    # if program terminated not by SIGKILL - exit
    if [ "$status" != "$killexit" ] ; then
        echo "exit $status"
        exit "$status"
    fi

    # otherwise sleep a bit and restart
    sleep 1
done