Files
smarm/tests/gen_server_shutdown.rs
T
claude 9c8f59ca53 feat(scheduler,supervisor,gen_server): graceful shutdown — request_shutdown, child Shutdown policy, handle_shutdown
Lift OTP's `exit(Pid, shutdown)` + child-spec `shutdown` wholesale.

scheduler / runtime
- `request_shutdown(pid)`: the polite stop. A target trapping exits gets an
  `ExitSignal { reason: DownReason::Shutdown }` on its trap inbox and keeps
  running; a non-trapping target is stopped as by `request_stop`, which is
  now documented as the hard stop (`exit(Pid, kill)`). Dead pid: no-op.
- `RuntimeHandle::request_shutdown` for the off-runtime (signal thread) path;
  `from == ROOT_PID` there.
- `DownReason::Shutdown` — appears only in ExitSignal, never in Down (a
  complying target exits *normally*).

supervisor
- `ChildSpec::shutdown(Shutdown::{BrutalKill, Timeout(d), Infinity})`,
  default Timeout(5s). Every supervisor-initiated stop (ordered shutdown and
  OneForAll/RestForOne sibling cycling) is: request_shutdown → await the
  child's Signal up to the grace → request_stop → await. Sequential, reverse
  start order.
- The supervisor traps exits; a Shutdown ExitSignal runs the ordered
  shutdown and `run()` returns normally, so `request_shutdown(root_sup)`
  tears a whole tree down top-down with each child's grace period.
- FIX: a hard `request_stop` on a supervisor previously orphaned its
  children (the ordered shutdown lived after the loop, and the unwind
  skipped it). `Live` (the by_pid map) now carries a drop guard that
  fire-and-forget hard-stops live children when unwinding.

gen_server
- `GenServerCtx::trap_exit()` opt-in in `init`; the trap inbox becomes arm 0
  of the loop's select. Shutdown ExitSignal → `handle_shutdown() ->
  ShutdownAction::{Exit, Continue}` (default Exit: loop breaks, `terminate`
  runs on the normal path and may block). Other ExitSignals →
  `handle_exit(sig)`.
- `GenServerCtx::stop_handle() -> StopHandle`, `stop()` ends the server
  after the current message with a *normal* exit — the missing
  `{stop, normal, State}`; `request_stop(self_pid())` was the only self-exit
  and it is abnormal (Transient restarts it).
- `GenServerRef::shutdown()` / `gen_server::shutdown(name)` now go through
  `request_shutdown`.

Tests: tests/shutdown.rs, tests/supervisor_shutdown.rs,
tests/gen_server_shutdown.rs. Full suite green; fmt + clippy --lib clean.
2026-08-19 06:34:48 +00:00

217 lines
6.8 KiB
Rust

//! gen_server graceful shutdown.
//!
//! - A server that does not opt in (`ctx.trap_exit()` in `init`) is stopped
//! outright by `request_shutdown`, exactly as by `request_stop`.
//! - A trapping server receives the request as `handle_shutdown`. The default
//! returns `ShutdownAction::Exit`: the loop breaks and `terminate` runs on
//! the normal (non-unwind) path, so it may block. `Continue` keeps the loop
//! dispatching; the state later ends itself with a `StopHandle` — the only
//! way for a gen_server to exit *normally* on its own (`request_stop` on
//! self is an abnormal `Stopped`, which `Transient` restarts).
//! - Other exit signals (linked peers dying) reach a trapping server via
//! `handle_exit`.
use smarm::gen_server::{
start, GenServer, GenServerBuilder, GenServerCtx, GenServerRef, ShutdownAction, StopHandle,
};
use smarm::supervisor::{ChildSpec, OneForOne, Restart};
use smarm::{link, monitor, request_shutdown, run, self_pid, sleep, spawn, DownReason, ExitSignal};
use std::sync::atomic::{AtomicBool, AtomicUsize, Ordering};
use std::sync::{Arc, Mutex};
use std::time::Duration;
#[derive(Default, Clone)]
struct Log {
events: Arc<Mutex<Vec<&'static str>>>,
}
impl Log {
fn push(&self, e: &'static str) {
self.events.lock().unwrap().push(e);
}
fn get(&self) -> Vec<&'static str> {
self.events.lock().unwrap().clone()
}
}
/// A server with configurable shutdown behaviour.
struct Srv {
log: Log,
trap: bool,
action: ShutdownAction,
stop: Option<StopHandle<Srv>>,
exits: Arc<Mutex<Vec<ExitSignal>>>,
}
impl Srv {
fn new(log: &Log, trap: bool, action: ShutdownAction) -> Self {
Srv {
log: log.clone(),
trap,
action,
stop: None,
exits: Default::default(),
}
}
}
enum Cast {
Note(&'static str),
StopNow,
}
impl GenServer for Srv {
type Call = ();
type Reply = ();
type Cast = Cast;
type Info = ();
type Timer = ();
fn init(&mut self, ctx: &GenServerCtx<Self>) {
if self.trap {
ctx.trap_exit();
}
self.stop = Some(ctx.stop_handle());
}
fn handle_call(&mut self, _: ()) {}
fn handle_cast(&mut self, c: Cast) {
match c {
Cast::Note(s) => self.log.push(s),
Cast::StopNow => self.stop.as_ref().unwrap().stop(),
}
}
fn handle_shutdown(&mut self) -> ShutdownAction {
self.log.push("handle_shutdown");
self.action
}
fn handle_exit(&mut self, sig: ExitSignal) {
self.log.push("handle_exit");
self.exits.lock().unwrap().push(sig);
}
fn terminate(&mut self) {
// Allowed to block on the graceful path.
if self.trap {
sleep(Duration::from_millis(10));
}
self.log.push("terminate");
}
}
fn spawn_settled<G: GenServer>(state: G) -> GenServerRef<G> {
let r = start(state);
sleep(Duration::from_millis(20)); // let init (trap_exit) run
r
}
#[test]
fn non_trapping_server_is_stopped_outright() {
let log = Log::default();
let l = log.clone();
run(move || {
let r = spawn_settled(Srv::new(&l, false, ShutdownAction::Exit));
let mon = monitor(r.pid());
request_shutdown(r.pid());
let d = mon.rx.recv().unwrap();
assert_eq!(d.reason, DownReason::Stopped);
});
assert_eq!(log.get(), vec!["terminate"]);
}
#[test]
fn trapping_server_exits_normally_via_handle_shutdown() {
let log = Log::default();
let l = log.clone();
run(move || {
let r = spawn_settled(Srv::new(&l, true, ShutdownAction::Exit));
let mon = monitor(r.pid());
request_shutdown(r.pid());
let d = mon.rx.recv().unwrap();
assert_eq!(d.reason, DownReason::Exit);
});
assert_eq!(log.get(), vec!["handle_shutdown", "terminate"]);
}
#[test]
fn continue_keeps_dispatching_until_stop_handle() {
let log = Log::default();
let l = log.clone();
run(move || {
let r = spawn_settled(Srv::new(&l, true, ShutdownAction::Continue));
let mon = monitor(r.pid());
request_shutdown(r.pid());
sleep(Duration::from_millis(20));
r.cast(Cast::Note("after-shutdown-request")).unwrap();
r.cast(Cast::StopNow).unwrap();
let d = mon.rx.recv().unwrap();
assert_eq!(d.reason, DownReason::Exit);
});
assert_eq!(
log.get(),
vec!["handle_shutdown", "after-shutdown-request", "terminate"]
);
}
#[test]
fn stop_handle_is_a_normal_exit_that_transient_does_not_restart() {
let starts = Arc::new(AtomicUsize::new(0));
let s = starts.clone();
run(move || {
let s2 = s.clone();
let sup = spawn(move || {
let s3 = s2.clone();
OneForOne::new()
.child(ChildSpec::new(Restart::Transient, move || {
s3.fetch_add(1, Ordering::SeqCst);
let log = Log::default();
let r = GenServerBuilder::new(Srv::new(&log, false, ShutdownAction::Exit))
.under(self_pid())
.start();
r.cast(Cast::StopNow).unwrap();
// Block until the server is gone; a bare spawn parent
// returning would not itself end the server.
let mon = monitor(r.pid());
let _ = mon.rx.recv();
}))
.run();
});
sup.join().unwrap(); // returns only if the child was not restarted forever
});
assert_eq!(starts.load(Ordering::SeqCst), 1);
}
#[test]
fn linked_peer_death_reaches_handle_exit() {
let log = Log::default();
let l = log.clone();
let alive = Arc::new(AtomicBool::new(false));
let a = alive.clone();
run(move || {
let r = spawn_settled(Srv::new(&l, true, ShutdownAction::Exit));
let pid = r.pid();
let peer = spawn(move || {
link(pid);
panic!("peer dies");
});
let _ = peer.join();
sleep(Duration::from_millis(20));
r.cast(Cast::Note("still-serving")).unwrap();
sleep(Duration::from_millis(20));
a.store(true, Ordering::SeqCst);
let mon = monitor(r.pid());
drop(r); // inbox closes → clean exit
let _ = mon.rx.recv(); // don't let the root-exit sweep race terminate
});
assert!(alive.load(Ordering::SeqCst));
assert_eq!(log.get(), vec!["handle_exit", "still-serving", "terminate"]);
}
#[test]
fn gen_server_ref_shutdown_is_graceful_for_a_trapping_server() {
let log = Log::default();
let l = log.clone();
run(move || {
let r = spawn_settled(Srv::new(&l, true, ShutdownAction::Exit));
r.shutdown();
});
assert_eq!(log.get(), vec!["handle_shutdown", "terminate"]);
}